An Event-Driven Multi Agent System for Scalable Traffic Optimization

Horn, G. and Przeźdiȩk, T. and Büscher, M. and Venticinque, S. and Aversa, R. and Martino, B.D. and Esposito, A. and Skrzypek, P. and Leznik, M. (2020) An Event-Driven Multi Agent System for Scalable Traffic Optimization. In: Workshops of the International Conference on Advanced Information Networking and Applications. Advances in Intelligent Systems and Computing . Springer, Cham, pp. 1373-1382. ISBN 9783030440374

Full text not available from this repository.

Abstract

Global demand for mobility will grow from 44 trillion to 122 trillion passenger-kilometres by 2050, and freight demand will triple in that time increasing traffic emissions by 60%. With current innovation and policy measures we are ‘on course for a 3.2C temperature rise’, according to the 2019 UN Emissions Gap Report. Nothing short of revolutionary is required to address this emergency. However, there is hope: shared mobility and widespread adoption of autonomous vehicles could cut emissions by 73% and congestion by 24% if managed by appropriate policies. This paper presents a vision and a concept for future distributed management systems for complex multi-modal transport networks that exploit Multi Agent Systems (MAS) to support individual actors based on data collected from heterogeneous sources like vehicles, freight items, infrastructures, Global Positioning Systems (GPS); and simulations of the behaviour of the many different actors involved in the transport system. Event driven approaches are envisioned to react and respond to real-time events efficiently. The main objective is to identify the best optimization strategies to reduce traffic emissions and maximize the use of the public infrastructures and shared mobility. Motivations, expected impacts, and challenges are also discussed.

Item Type:
Contribution in Book/Report/Proceedings
Subjects:
ID Code:
143965
Deposited By:
Deposited On:
22 Jan 2021 11:15
Refereed?:
Yes
Published?:
Published
Last Modified:
03 Mar 2021 14:58